1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294
|
/*
* Copyright 2007 Rob Kendrick <rjek@netsurf-browser.org>
* Copyright 2004-2007 James Bursa <bursa@users.sourceforge.net>
* Copyright 2003 Phil Mellor <monkeyson@users.sourceforge.net>
* Copyright 2003 John M Bell <jmb202@ecs.soton.ac.uk>
* Copyright 2004 John Tytgat <John.Tytgat@aaug.net>
*
* This file is part of NetSurf, http://www.netsurf-browser.org/
*
* NetSurf is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; version 2 of the License.
*
* NetSurf is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <assert.h>
#include <ctype.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/time.h>
#include <regex.h>
#include <time.h>
#include "utils/config.h"
#define NDEBUG
#include "utils/log.h"
#include "utils/messages.h"
#include "utils/utf8.h"
#include "utils/utils.h"
char * strip(char * const s)
{
size_t i;
for (i = strlen(s);
i != 0 && (s[i - 1] == ' ' || s[i - 1] == '\n' ||
s[i - 1] == '\r' || s[i - 1] == '\t');
i--)
;
s[i] = 0;
return s + strspn(s, " \t\r\n");
}
int whitespace(const char * str)
{
unsigned int i;
for (i = 0; i < strlen(str); i++)
if (!isspace(str[i]))
return 0;
return 1;
}
/**
* Replace consecutive whitespace with a single space.
*
* \param s source string
* \return heap allocated result, or 0 on memory exhaustion
*/
char * squash_whitespace(const char *s)
{
char *c = malloc(strlen(s) + 1);
int i = 0, j = 0;
if (!c)
return 0;
do {
if (s[i] == ' ' || s[i] == '\n' || s[i] == '\r' ||
s[i] == '\t') {
c[j++] = ' ';
while (s[i] == ' ' || s[i] == '\n' || s[i] == '\r' ||
s[i] == '\t')
i++;
}
c[j++] = s[i++];
} while (s[i - 1] != 0);
return c;
}
/**
* Converts NUL terminated UTF-8 encoded string s containing zero or more
* spaces (char 32) or TABs (char 9) to non-breaking spaces
* (0xC2 + 0xA0 in UTF-8 encoding).
*
* Caller needs to free() result. Returns NULL in case of error. No
* checking is done on validness of the UTF-8 input string.
*/
char *cnv_space2nbsp(const char *s)
{
const char *srcP;
char *d, *d0;
unsigned int numNBS;
/* Convert space & TAB into non breaking space character (0xA0) */
for (numNBS = 0, srcP = (const char *)s; *srcP != '\0'; ++srcP)
if (*srcP == ' ' || *srcP == '\t')
++numNBS;
if ((d = (char *)malloc((srcP - s) + numNBS + 1)) == NULL)
return NULL;
for (d0 = d, srcP = (const char *)s; *srcP != '\0'; ++srcP) {
if (*srcP == ' ' || *srcP == '\t') {
*d0++ = 0xC2;
*d0++ = 0xA0;
} else
*d0++ = *srcP;
}
*d0 = '\0';
return d;
}
/**
* Check if a directory exists.
*/
bool is_dir(const char *path)
{
struct stat s;
if (stat(path, &s))
return false;
return S_ISDIR(s.st_mode) ? true : false;
}
/**
* Compile a regular expression, handling errors.
*
* Parameters as for regcomp(), see man regex.
*/
void regcomp_wrapper(regex_t *preg, const char *regex, int cflags)
{
int r;
r = regcomp(preg, regex, cflags);
if (r) {
char errbuf[200];
regerror(r, preg, errbuf, sizeof errbuf);
fprintf(stderr, "Failed to compile regexp '%s'\n", regex);
die(errbuf);
}
}
/** We can have a fairly good estimate of how long the buffer needs to
* be. The unsigned long can store a value representing a maximum size
* of around 4 GB. Therefore the greatest space required is to
* represent 1023MB. Currently that would be represented as "1023MB" so 12
* including a null terminator.
* Ideally we would be able to know this value for sure, in the mean
* time the following should suffice.
**/
#define BYTESIZE_BUFFER_SIZE 20
/**
* Does a simple conversion which assumes the user speaks English. The buffer
* returned is one of three static ones so may change each time this call is
* made. Don't store the buffer for later use. It's done this way for
* convenience and to fight possible memory leaks, it is not necessarily pretty.
**/
char *human_friendly_bytesize(unsigned long bsize) {
static char buffer1[BYTESIZE_BUFFER_SIZE];
static char buffer2[BYTESIZE_BUFFER_SIZE];
static char buffer3[BYTESIZE_BUFFER_SIZE];
static char *curbuffer = buffer3;
float bytesize = (float)bsize;
if (curbuffer == buffer1)
curbuffer = buffer2;
else if (curbuffer == buffer2)
curbuffer = buffer3;
else
curbuffer = buffer1;
enum {bytes, kilobytes, megabytes, gigabytes} unit = bytes;
static char units[][7] = {"Bytes", "kBytes", "MBytes", "GBytes"};
if (bytesize > 1024) {
bytesize /= 1024;
unit = kilobytes;
}
if (bytesize > 1024) {
bytesize /= 1024;
unit = megabytes;
}
if (bytesize > 1024) {
bytesize /= 1024;
unit = gigabytes;
}
sprintf(curbuffer, "%3.2f%s", bytesize, messages_get(units[unit]));
return curbuffer;
}
/**
* Create an RFC 1123 compliant date string from a Unix timestamp
*
* \param t The timestamp to consider
* \return Pointer to buffer containing string - invalidated by next call.
*/
const char *rfc1123_date(time_t t)
{
static char ret[30];
struct tm *tm = gmtime(&t);
const char *days[] = { "Sun", "Mon", "Tue", "Wed", "Thu", "Fri", "Sat" },
*months[] = { "Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec" };
snprintf(ret, sizeof ret, "%s, %02d %s %d %02d:%02d:%02d GMT",
days[tm->tm_wday], tm->tm_mday, months[tm->tm_mon],
tm->tm_year + 1900, tm->tm_hour, tm->tm_min,
tm->tm_sec);
return ret;
}
/**
* Case insensitive strstr implementation
*
* \param haystack String to search in
* \param needle String to look for
* \return Pointer to start of found substring, or NULL if not found
*/
char *strcasestr(const char *haystack, const char *needle)
{
size_t needle_len = strlen(needle);
const char * last_start = haystack + (strlen(haystack) - needle_len);
while (haystack <= last_start) {
if (strncasecmp(haystack, needle, needle_len) == 0)
return (char *)haystack;
haystack++;
}
return NULL;
}
/**
* Returns a number of centiseconds, that increases in real time, for the
* purposes of measuring how long something takes in wall-clock terms. It uses
* gettimeofday() for this. Should the call to gettimeofday() fail, it returns
* zero.
*
* \return number of centiseconds that increases monotonically
*/
unsigned int wallclock(void)
{
struct timeval tv;
if (gettimeofday(&tv, NULL) == -1)
return 0;
return ((tv.tv_sec * 100) + (tv.tv_usec / 10000));
}
#ifndef HAVE_STRNDUP
/**
* Duplicate up to n characters of a string.
*/
char *strndup(const char *s, size_t n)
{
size_t len;
char *s2;
for (len = 0; len != n && s[len]; len++)
continue;
s2 = malloc(len + 1);
if (!s2)
return 0;
memcpy(s2, s, len);
s2[len] = 0;
return s2;
}
#endif
|